尚靖桓 Jinghuan Shang

I'm a Ph.D. candidate in the Department of Computer Science at Stony Brook University, working with Prof. Michael Ryoo, as a part of CV Lab at Stony Brook. I received my Bachelor's degree from IEEE Honored Class at Shanghai Jiao Tong University (SJTU) in 2018, with honor from Shanghai.

Research interest: Representation Learning, Robotics, and Computer Vision. Specifically, I find good visual representations for robots to perform visual tasks under reinforcement learning and imitation learning settings.

[CV][GitHub] Email: jishang [at] cs &dot& stony brook %dot% edu

News

2022/07 - StARformer is accepted to ECCV 2022! See how local representations benefit long-term sequence modeling in vision-based RL.

2022/06 - Robot Sim to Reeeaaaal? Check TRITON using neural neural texture and differentiable rendering!

2022/06 - Introducing 3D Token Representation Layer, a light-weighted, plug-and-play module for Transformer to learn viewpoint-agnostic representations, which enables vision models to generalize to different view angles!

2021/06 - Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels? We conducted studies on this question and our pre-print paper is available on Arxiv!

2021/06 - Our paper on Third-Person Imitation Learning is Accepted by IROS 2021!

Publications and Preprints

Neural Neural Textures Make Sim2Real Consistent
R. Burgert, J. Shang, X. Li, and M. S. Ryoo
arXiv: 2206.13500
[Project Page] [Code -- Coming Soon] [arXiv]
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
J. Shang, S. Das, and M. S. Ryoo
arXiv: 2206.11895
[Project Page] [Code -- Coming Soon] [arXiv]
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
X. Li, J. Shang, S. Das, and M. S. Ryoo
arXiv: 2206.05266
[arXiv]
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
J. Shang, K. Kahatapitiya, X. Li, and M. S. Ryoo
ECCV 2022
[arXiv] [Code]
Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning
J. Shang and M. S. Ryoo
IROS 2021
[arXiv] [Talk] [Digest Slide]

Honors and Awards

2018/08- Merit Scholarship from the Department of Computer Science at Stony Brook University
2018/06- Outstanding graduate among all graduates from universities in Shanghai
2016- 1st Prize in Shanghai Division of China Undergraduate Mathematical Contest in Modeling (CUMCM)
2015-2017- 3 times of Academic Excellence Scholarship at Shanghai Jiao Tong University

Fun

I love cooking.

I solve some algorithm problems in my spare time. Luckily got Top 10 in 2020 SBU ICPC Slection Contest. Here is my [Leetcode].

Last modified 2022/06. Style Credit: latex.css